Update app.py

app.py

@@ -12,6 +12,36 @@ import pandas as pd
 # Define the list of tickers
 tickers = ['TSLA', 'PLTR', 'SOUN', 'MSFT']
 
+# Company name to ticker mapping for better query handling
+company_to_ticker = {
+    'tesla': 'TSLA',
+    'palantir': 'PLTR',
+    'soundhound': 'SOUN',
+    'microsoft': 'MSFT',
+    'nvidia': 'NVDA',
+    'google': 'GOOG',
+    'amazon': 'AMZN',
+    'apple': 'AAPL',
+    'meta': 'META',
+    'netflix': 'NFLX',
+    'intel': 'INTC',
+    'amd': 'AMD',
+    'ibm': 'IBM',
+    'oracle': 'ORCL',
+    'cisco': 'CSCO',
+    'jpmorgan': 'JPM',
+    'bank of america': 'BAC',
+    'wells fargo': 'WFC',
+    'visa': 'V',
+    'mastercard': 'MA',
+    'exxon': 'XOM',
+    'chevron': 'CVX',
+    'pfizer': 'PFE',
+    'johnson & johnson': 'JNJ',
+    'merck': 'MRK',
+    'spy': 'SPY'
+}
+
 # Prefetch stock data for all tickers at startup using yfinance
 all_data = {}
 try:
@@ -22,14 +52,14 @@ except Exception as e:
     print(f"Error prefetching data: {e}")
     all_data = {ticker: pd.DataFrame() for ticker in tickers}  # Initialize empty DataFrames on failure
 
-# Create a DataFrame with 'Adj Close' columns for each ticker using pd.concat to handle varying lengths
+# Create a DataFrame with 'Adj Close' columns for each ticker
 series_list = []
 for ticker, data in all_data.items():
     if not data.empty:
         s = data['Close']
         s.name = ticker
         series_list.append(s)
-adj_close_data = pd.concat(series_list, axis=1)
+adj_close_data = pd.concat(series_list, axis=1) if series_list else pd.DataFrame()
 
 # Display the first few rows to verify (for debugging; remove in production)
 print(adj_close_data.head())
@@ -54,13 +84,21 @@ def fetch_stock_data(symbol, start_date, end_date):
             return None
 
 def parse_dates(query):
-    # Enhanced to handle year ranges like "between 2010 and 2020"
+    # Handle year ranges like "between 2010 and 2020"
     range_match = re.search(r'between\s+(\d{4})\s+and\s+(\d{4})', query.lower())
     if range_match:
         start_year = int(range_match.group(1))
         end_year = int(range_match.group(2))
-        return datetime(start_year, 1, 1), datetime(end_year, 12, 31)
-    # Fallback to original period parsing for recent periods
+        try:
+            start_date = datetime(start_year, 1, 1)
+            end_date = datetime(end_year, 12, 31)
+            if start_date >= end_date:
+                raise ValueError("Start date must be before end date")
+            return start_date, end_date
+        except ValueError as e:
+            print(f"Date parsing error: {e}")
+            return None, None
+    # Fallback to period parsing for recent periods
     period_match = re.search(r'(\d+)\s*(year|month|week|day)s?', query.lower())
     if period_match:
         num = int(period_match.group(1))
@@ -85,72 +123,14 @@ def parse_dates(query):
 
 def find_closest_symbol(input_symbol):
     input_symbol = input_symbol.upper()
+    # Check if input matches a company name
+    for company, ticker in company_to_ticker.items():
+        if company in input_symbol.lower():
+            return ticker
+    # Fallback to ticker matching
     closest = difflib.get_close_matches(input_symbol, available_symbols, n=1, cutoff=0.6)
     return closest[0] if closest else None
 
 def calculate_growth_rate(start_date, end_date, symbol):
     hist = fetch_stock_data(symbol, start_date.strftime('%Y-%m-%d'), end_date.strftime('%Y-%m-%d'))
-    if hist is None or hist.empty or 'Close' not in hist.columns:
-        return None
-    beginning_value = hist.iloc[0]['Close']
-    ending_value = hist.iloc[-1]['Close']
-    years = (end_date - start_date).days / 365.25
-    if years <= 0:
-        return 0
-    total_return = ending_value / beginning_value
-    cagr = total_return ** (1 / years) - 1
-    return cagr * 100
-
-def calculate_investment(principal, years, annual_return=0.07):
-    return principal * (1 + annual_return) ** years
-
-model_name = "HuggingFaceTB/SmolLM-135M-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    device_map="auto",
-)
-
-def generate_response(user_query, enable_thinking=False):
-    stock_keywords = ['stock', 'growth', 'investment', 'price', 'return', 'cagr']
-    is_stock_query = any(keyword in user_query.lower() for keyword in stock_keywords)
-    summary = ""
-    if is_stock_query:
-        symbol_match = re.search(r'\b([A-Z]{1,5})\b', user_query.upper())
-        symbol = find_closest_symbol(symbol_match.group(1)) if symbol_match else None
-        if symbol:
-            start_date, end_date = parse_dates(user_query)
-            hist = fetch_stock_data(symbol, start_date.strftime('%Y-%m-%d'), end_date.strftime('%Y-%m-%d'))
-            if "average price" in user_query.lower():
-                if hist is not None and not hist.empty and 'Close' in hist.columns:
-                    avg_price = hist['Close'].mean()
-                    summary = f"The average adjusted closing price for {symbol} from {start_date.strftime('%Y-%m-%d')} to {end_date.strftime('%Y-%m-%d')} is ${avg_price:.2f}."
-            elif "cagr" in user_query.lower() or "return" in user_query.lower():
-                growth_rate = calculate_growth_rate(start_date, end_date, symbol)
-                if growth_rate is not None:
-                    summary = f"The CAGR for {symbol} over the period from {start_date.strftime('%Y-%m-%d')} to {end_date.strftime('%Y-%m-%d')} is {growth_rate:.2f}%."
-                else:
-                    summary = f"No data available for {symbol} in the specified period."
-            investment_match = re.search(r'\$(\d+)', user_query)
-            if investment_match:
-                principal = float(investment_match.group(1))
-                years = (end_date - start_date).days / 365.25
-                projected = calculate_investment(principal, years)
-                summary += f" Projecting ${principal} at 7% return over {years:.1f} years: ${projected:.2f}."
-    system_prompt = (
-        "You are FinChat, a knowledgeable financial advisor. Always respond in a friendly, professional manner. "
-        "For greetings like 'Hi' or 'Hello', reply warmly, e.g., 'Hi! I'm FinChat, your financial advisor. What can I help you with today regarding stocks, investments, or advice?' "
-        "Provide accurate, concise advice based on data."
-    )
-    # Placeholder for generation logic (tokenize, generate, decode)
-    return summary or "Please provide a specific stock or investment query."
-
-# Gradio interface setup
-demo = gr.Interface(
-    fn=generate_response,
-    inputs=[gr.Textbox(lines=2, placeholder="Enter your query (e.g., 'TSLA CAGR between 2010 and 2020')"), gr.Checkbox(label="Enable Thinking")],
-    outputs="text",
-    title="FinChat",
-    description="Ask about stock performance, CAGR, or investments."
-)
-demo.launch()
+    if hist is